JL
Jiafei Lyu
cs.LGcs.AIcs.CLcs.CVcs.ROstat.ML
On Valency
published · living versionsW_89re7bev·v1 · currentpublished
Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability
with Guodong Zheng, Yan Sun, Peng Wang, Enneng Yang +3
1 version
W_w4wr4u5m·v1published
Preprints & journals
33 papers in the corpus · 2021–2026Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability2610.31551v1 · Guodong Zheng, Yan Sun, Peng Wang et al.2026 · 0 citationsarXivon Valency
CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents2610.29965v1 · Wenhao Yu, Zhengcheng Wang, Jiahong Liu et al.2026 · 0 citationsarXivon Valency
Process Reward Modeling with Reliability- and Conservatism-Aware Bayesian Belief2610.23223v1 · Zhongjian Qiao, Zhixiang Zhou, Jiafei Lyu et al.2026 · 0 citationsarXiv
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms2608.27409v2 · Siye Wu, Kai Yang, Yuchen Cai et al.2026 · 0 citationsarXiv
Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets2605.24862v1 · Zhongjian Qiao, Jiafei Lyu, Chenjia Bai et al.2026 · 0 citationsarXiv
Debiased Model-based Representations for Sample-efficient Continuous Control2605.11711v1 · Jiafei Lyu, Zichuan Lin, Scott Fujimoto et al.2026 · 0 citationsarXiv
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience2603.24533v1 · Zichuan Lin, Feiyu Liu, Yijun Yang et al.2026 · 0 citationsarXiv
Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting2603.08118v1 · Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu et al.2026 · 0 citationsarXiv
Temporal Difference Learning with Constrained Initial Representations2602.11800v1 · Jiafei Lyu, Jingwen Yang, Zhongjian Qiao et al.2026 · 0 citationsarXiv
ProAct: Agentic Lookahead in Interactive Environments2602.05327v1 · Yangbin Yu, Mingyu Yang, Junyou Li et al.2026 · 1 citationarXiv
Cross-Domain Offline Policy Adaptation via Selective Transition Correction2602.05776v1 · Mengbei Yan, Jiafei Lyu, Shengjie Sun et al.2026 · 0 citationsarXiv
Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering2512.02435v4 · Zhongjian Qiao, Rui Yang, Jiafei Lyu et al.2025 · 0 citationsarXiv
Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts2512.02486v2 · Zhongjian Qiao, Rui Yang, Jiafei Lyu et al.2025 · 0 citationsarXiv
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning2505.23871v2 · Zeyuan Liu, Zhihe Yang, Jiawei Xu et al.2025 · 0 citationsarXiv
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning2504.00891v2 · Jian Zhao, Runze Liu, Kaiyan Zhang et al.2025 · 3 citationsarXiv
VLP: Vision-Language Preference Learning for Embodied Manipulation2502.11918v1 · Runze Liu, Chenjia Bai, Jiafei Lyu et al.2025 · 3 citationsarXiv
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning2412.15517v1 · Yangkun Chen, Kai Yang, Jian Tao et al.2024 · 4 citationsarXiv
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning2410.20750v1 · Jiafei Lyu, Kang Xu, Jiacheng Xu et al.2024 · 3 citationsarXiv
A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning2410.14660v1 · Shengjie Sun, Runze Liu, Jiafei Lyu et al.2024 · 21 citationsarXiv
SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning2408.12970v2 · Zhongjian Qiao, Jiafei Lyu, Kechen Jiao et al.2024 · 4 citationsarXiv
A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation2407.00496v1 · Aicheng Gong, Kai Yang, Jiafei Lyu et al.2024 · 26 citationsarXiv
World Models with Hints of Large Language Models for Goal Achieving2406.07381v1 · Zeyuan Liu, Ziyu Huan, Xiyao Wang et al.2024 · 1 citationarXiv
Cross-Domain Policy Adaptation by Capturing Representation Mismatch2405.15369v1 · Jiafei Lyu, Chenjia Bai, Jingwen Yang et al.2024 · 2 citationsarXiv
SEABO: A Simple Search-Based Method for Offline Imitation Learning2402.03807v2 · Jiafei Lyu, Xiaoteng Ma, Le Wan et al.2024 · 2 citationsarXiv
Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence2402.02701v2 · Jiafei Lyu, Le Wan, Xiu Li et al.2024 · 7 citationsarXiv
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model2311.13231v3 · Kai Yang, Jian Tao, Jiafei Lyu et al.2023 · 53 citationsarXiv
Normalization Enhances Generalization in Visual Reinforcement Learning2306.00656v1 · Lu Li, Jiafei Lyu, Guozheng Ma et al.2023 · 6 citationsarXiv
Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse2305.18443v1 · Jiafei Lyu, Le Wan, Zongqing Lu et al.2023 · 15 citationsarXiv
Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination2206.07989v2 · Jiafei Lyu, Xiu Li, Zongqing Lu2022 · 13 citationsarXiv
Mildly Conservative Q-Learning for Offline Reinforcement Learning2206.04745v3 · Jiafei Lyu, Xiaoteng Ma, Xiu Li et al.2022 · 56 citationsarXiv
Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients2112.11216v1 · Jiafei Lyu, Yu Yang, Jiangpeng Yan et al.2021 · 14 citationsarXiv
Efficient Continuous Control with Double Actors and Regularized Critics2106.03050v1 · Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan et al.2021 · 65 citationsarXiv
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning2102.12962v3 · Rui Yang, Jiafei Lyu, Yu Yang et al.2021 · 2 citationsarXiv
Career total: 45 works. 33 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.